Agent Cost MCP Server
@vk0/agent-cost-mcp
npm
v2.3.3
Source verified
Published by vk0dev — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Local-first MCP server for Claude Code cost analysis, budgets, forecasts, anomalies, and subagent-aware optimization from local JSONL session logs.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 3 = 97. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −3 | capability blast radius (moderate) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 1
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([get_session_cost]) co-exist with external-action tools ([set_monitor_webhook]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [get_session_cost] → sinks [set_monitor_webhook]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow get_session_cost → set_monitor_webhook
Tools 11
Each tool and what it can reach — statically extracted from the published source.
get_session_costingests untrusted inputset_monitor_webhooknetwork egressconfigure_budgetno sensitive capabilitydetect_cost_anomaliesno sensitive capabilityestimate_run_costno sensitive capabilityget_cost_forecastno sensitive capabilityget_cost_trendno sensitive capabilityget_subagent_treeno sensitive capabilityget_tool_roino sensitive capabilityget_tool_usageno sensitive capability
Show 1 more tool ↓
suggest_optimizationsno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (11 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v2.3.3 latest |
A 97/100 | 1 | 1.13.0 | 2026-09-08 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @vk0/agent-cost-mcp --onlineMore in AI & Agents
Authenticated MCP transport with HTTP Signatures for AAuth agents
Local-first MCP server for parallel AI coding agents to claim file ownership before edits, preventing stomping on each other in the same worktree.
Agent-agnostic intercommunication system — sessions, messaging, channels, shared state, and real-time events
MCP server for AI agent task communication and delegation with diagnostic lifecycle visibility
Programmatic add/link/unlink for MCP servers across 23 AI coding agents (Claude Code, Claude Desktop, Cursor, VS Code, Codex, Gemini CLI, Zed, Cline, OpenCode, Goose, Kiro, Windsurf, and more). Functional API with dry-run support.
MCP server layer exposing agent-mesh orchestrator as an MCP agent